finetune_teacher_clean_mozilla_100_epochs_try2
This model is a fine-tuned version of finetune_teacher_clean_mozilla_200_epochs on the None dataset. It achieves the following results on the evaluation set:
- Loss: 55.2160
- Wer: 0.2810
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 42.7428 | 29.41 | 1000 | 48.0854 | 0.3160 |
| 45.9744 | 58.82 | 2000 | 50.4082 | 0.2936 |
| 30.0353 | 88.23 | 3000 | 55.2160 | 0.2810 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2